Neighborhood selection and rules identification for cellular automata: a rough sets approach

Abstract. In this paper a method is proposed which uses data mining techniques based on rough sets theory to select neighborhood and deter-mine update rule for cellular automata (CA). According to the proposed approach, neighborhood is detected by reducts calculations and a rule-learning algorithm is applied to induce a set of decision rules that define the evolution of CA. Experiments were performed with use of synthetic as well as real-world data sets. The results show that the introduced method allows identification of both deterministic and probabilistic CA-based models of real-world phenomena.